Virtual Machine and dataset for Multi-channel MRI segmentation of eye structures and tumors using patient-specific features
Lists
Only you see this
Abstract
% Plos One Journal - http://dx.doi.org/10.1371/journal.pone.0173900<br> % ##################################<br> % ''Multi-channel MRI segmentation of eye structures and tumors using <br> % patient-specific features''<br> % ##################################<br> %<br> % C. Ciller, S.I. De Zanet, K. Kamnitsas, P. Maeder, B. Glocker, <br> % F.L. Munier, D. Rueckert, J-P. Thiran, M.B. Cuadra* and R. Sznitman* *Equally contributed authors % Copyright (c) - All rights reserved. University of Lausanne. 2016. The content of these folders include all the necessary steps for compu-<br> ting the automatic segmentation of eye structures and tumors in 3D MRI.<br> Upon acceptance of this manuscript, all the experiments and a working<br> copy of the software will be made available for its use. % Requirements:<br> %%%%%%%%%%%%%%%%%%%%%<br> Software:<br> - VirtualBox<br> - Matlab R2014a and superior<br> - Mac OS X / Linux / Windows Hardware:<br> - 25 GB Free Disk (Virtual Image)<br> - 4/8 GB of RAM<br> - Nvidia (R) GPU (GTX 970 or superior) with CUDA/cuDNN capabilities. % 1_EyeSegmentation :<br> %%%%%%%%%%%%%%%%%%%%% admin_password: plosone This section Covers the EyeModeler software for the segmentation of eye<br> structures in 3D MRI. It contains a working copy of the software deve-<br> loped for the automatic segmentation of eye structures in 3D MRI. For the sake of simplicity we offer a video representing the process of<br> segmentation https://youtu.be/0n5Wz8RPQ7w % 2_PlosOne_RF_Experiments :<br> %%%%%%%%%%%%%%%%%%%%%%%%%%%% Here we cover the first round of experiments with a Random Forest confi-<br> guration using the output of the previous step. % 3_PlosOne_CNN_Experiments :<br> %%%%%%%%%%%%%%%%%%%%%%%%%%%%% This section covers the procedure for training the DeepMedic CNN model.<br> The original code can be found in: https://github.com/Kamnitsask/deepmedic The code in this section is modified to be able to cope with a varying<br> number of input channels [6,9] and a leave-one-out training configuration % 4_EyeTumorSegment_Graphcut :<br> %%%%%%%%%%%%%%%%%%%%%%%%%%%%%% Here we perform the final graph-cut refinement on the output of the <br> experiments with different classifiers. For the sake of simplicity, we have configured the graph-cut optimization<br> on the Random Forest experiments proposed in this manuscript.
BibTeX
@inproceedings{ciller2017virtual,
author = {Carlos Ciller and Sandro De Zanet and Konstantinos Kamnitsas and Philippe Maeder and Ben Glocker and Francis L. Munier and Daniel Rueckert and Jean‐Philippe Thiran and Meritxell Bach Cuadra and Raphael Sznitman},
title = {{Virtual Machine and dataset for Multi-channel MRI segmentation of eye structures and tumors using patient-specific features}},
booktitle = {Zenodo},
year = {2017},
doi = {10.5281/zenodo.400920},
}Loading related content...